AI News

StageGuard: Physiologically Constrained Sleep Staging (arxiv.org)

Group Preference Collapse in Personalized Multimodal Large Language Models (arxiv.org)

Not All LLM Reasoning is Visible in the Chain-of-Thought (arxiv.org)

ESRVS: Extreme Semi-Supervised Retinal Vessel Segmentation with a Single Annotated Image (arxiv.org)

Certified Parallel-in-Time Sinkhorn for Dynamic Entropic Optimal Transport (arxiv.org)

Forecasting the Emergence and Evolution of Crash Hotspots: A Unified Deep Learning Framework for Proactive Traffic Safety (arxiv.org)

Beyond Error-vs-Discard Characteristic: Toward Stable and Reliable Evaluation for Face Image Quality Assessment (arxiv.org)

ML-based Predictive Models for Power Consumption in Virtualised O-RANs (arxiv.org)

xMIx: High-Performance Serving-Time Platform for Mechanistic Interpretability Apps (arxiv.org)

HyCE-RAG: Hypergraph Chain-of-Evidence Retrieval-Augmented Generation for Explainable Multi-hop Question Answering (arxiv.org)

Aortic Valve Disease Screening from PPG via Physiology-Guided Self-Supervised Learning (arxiv.org)

Discrepancy-Rounded Fair Bandits with Static and Time-Varying Exposure Floors (arxiv.org)

Weighted Low-Rank Matrix Approximation: Acceleration and Applications (arxiv.org)

Understanding Tone-Dependent Inference Cost in Large Language Models (arxiv.org)

Sign-Symmetry Learning Rules are Robust Fine-Tuners (arxiv.org)

DeepLook: Deeper Thinking with Lookahead (arxiv.org)

Bitcoin Price Direction Prediction via Regime-Aware Multi-Modal Fusion of Social Sentiment and Technical Features (arxiv.org)

LanteRn: Latent Visual Structured Reasoning (arxiv.org)

Adversarial Test-Hardening for AI-Written Code: An Instrument Autopsy and a Pre-Registered Causal Estimate of the Critic Loop (arxiv.org)

Hierarchical Soft Actor-Critic for Sparse-Reward Long-Horizon Reinforcement Learning (arxiv.org)

Gradient Networks for Universal Magnetic Modeling of Synchronous Machines (arxiv.org)

AlloBench: Measuring Online Tool Allocation Capability in LLM Agents (arxiv.org)

Reason-Mediated Behavioral Models for Auditing LLM Social Simulators (arxiv.org)

When Should Active RAG Retrieve? A Budget-Aware Evaluation of Utility, Calibration, and Cost (arxiv.org)

Chart Deception in Vision-Language Models: From Vulnerability to Mitigation (arxiv.org)

When Can Depth Replace Precision? A Resource Theory of Quantized Neural Computation (arxiv.org)

CausalGate: Causal Importance Distillation for Transformer Module Pruning (arxiv.org)

Minimax Lower Bounds of Kernel Discrepancy Estimation: MMD, HSIC, KSD (arxiv.org)

Cortex: Compact Behavior Cloning for Quake with Frozen Visual Features (arxiv.org)

MixQuant: Adaptive Mixed-Precision Quantization for Large Language Models (arxiv.org)

Masked Autoencoders Learn Perception-Relevant Representations from Resting State Neural Data (arxiv.org)

Trustworthy Medical Segmentation: Uncertainty-Aware U-Net Evaluation Under Clinical Image Degradation (arxiv.org)

Revitalizing Public Urban Places through Cultural and Political Memory: A Technological Approach with LLMs and Augmented Reality (arxiv.org)

Forgetting is Everywhere (arxiv.org)

Towards Nexus-Score: Metadata Gaps Limit Scholarly AI Attribution (arxiv.org)

Controllable Diversity in Normalization-Based Implicit Ensembles via Softmax-Temperature Modulation (arxiv.org)

MobiWave: Dispatch-Oriented Graph Wavelets and Drift-Guided Selective Optimization for Autonomous Fleet Rebalancing (arxiv.org)

Nanbeige4.2-3B: Unlocking Agentic Capabilities in a Compact Model (arxiv.org)

Beyond Aggregate Risk: Role-Stratified Conformal Risk Control for LLM Tool Calls (arxiv.org)

Seesaw: Accelerating Training by Balancing Learning Rate and Batch Size Scheduling (arxiv.org)

A Few Words Go a Long Way: Language Guided Robot Policy Synthesis (arxiv.org)

EmotionAI: A Privacy-Preserving Computational Intelligence Pipeline for Speech-Emotion-Grounded Conversational Analysis (arxiv.org)

Execution-Grounded Security Testing for Coding Agents in Software Engineering Pipelines (arxiv.org)

KG2Code: Bridging Knowledge Graphs and Large Language Models via Executable Code for Question Answering (arxiv.org)

In-Context Learning as Implicit Policy Gradient (arxiv.org)

VLASH: Real-Time VLAs via Future-State-Aware Asynchronous Inference (arxiv.org)

The Intruder Threshold: A Spectral Law for LoRA Fine-Tuning (arxiv.org)

LEX-EC: A Lexical Evidence-Channel Audit Framework for Zero-Shot LLM Personality Classification in Black-Box Settings (arxiv.org)

Cheap Probes Predict Expensive Training in 3D-CT Vision--Language Models (arxiv.org)

Identification and Learning of Semantic Observation Kernels: Partial Observation, Uniform Recovery, & Minimax Limits (arxiv.org)